Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    uphill

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arLayout
    -0.07
    .Act
    -0.07
     genu
    -0.07
     AtomicInteger
    -0.07
     Execution
    -0.07
     hvor
    -0.06
    (Order
    -0.06
     ++)↵
    -0.06
     followers
    -0.06
    ･･
    -0.06
    POSITIVE LOGITS
    READING
    0.07
    -fi
    0.07
     avalanche
    0.06
    ILL
    0.06
    _csv
    0.06
    ينا
    0.06
    yyyyMMdd
    0.06
    育
    0.06
     тай
    0.06
    �
    0.06
    Act Density 0.004%

    No Known Activations